Emily's eight-year-old son has worn hearing aids since he was six months old and has outgrown more earmolds than she can count. His experience, along with others, is driving a cutting‑edge Western University-led project that could change pediatric hearing‑aid care globally.
The new ALLEars project, a large-scale collaboration between Western and Boys Town National Research Hospital in Nebraska, uses predictive artificial intelligence and 3D printing to reimagine how pediatric earmolds are made.
The World Health Organization estimates that 34 million children worldwide are deaf or hard of hearing. Early intervention can ensure access to signed or spoken language, supporting speech, language and social development. Hearing aids are a widely used option for improving access to sound, but children's hearing aids depend on soft custom earmolds to function correctly.
Those earmolds present a persistent challenge. Each one must be tailor‑made to a child's ear, yet rapid early‑childhood growth means they quickly become too small. As a result, families often face recurring periods of outgrowing earmolds, leading to times when children cannot hear as clearly as they should - a problem the new ALLEars project aims to solve.
"In the first few years of life, children are going through a really rapid period of growth," said Susan Scollie, professor in the Faculty of Health Sciences at Western, an audiologist and lead on the ALLEars project. "That growth can repeatedly interrupt their hearing aid use during the critical language development years."
A new model: Predict, print and prepare in advance
The ALLEars project aims to solve that problem using AI-driven growth prediction.
The project will allow researchers to digitally scan an impression of a child's ear, use AI to predict how it will change and 3D-print future earmolds in advance. Instead of reacting to growth, audiologists can stay ahead of it, reducing wait times, appointments and costs.
"We're bringing a completely fresh and new high-tech approach to an old problem: kids outgrowing their earmolds faster than we can make them," said Scollie, a professor in the School of Communication Sciences and Disorders.
The project was made possible by a $4.4-million (USD) grant over four years from the Oberkotter Foundation, which funds programs improving listening, spoken language and literacy outcomes for children who are deaf or hard of hearing.
"The ALLEars project is a powerful example of what happens when bold ideas meet a real need within pediatric hearing health care," said Teresa Caraway, CEO of the Oberkotter Foundation. "By using innovative and rapidly evolving technology to address long-standing challenges in delivering quality care, this project will accelerate solutions and make a tangible difference in the lives of children who are deaf or hard of hearing."
The transformative funding was awarded to Western due to its renowned audiology expertise - anchored in research at the National Centre for Audiology and evidence-based care at the on-campus H.A. Leeper Speech & Hearing Clinic - as well as its strengths in artificial intelligence and 3D printing.
"As a global leader in audiology and biomedical engineering, Western brings clinician-scientists and engineers together to improve care and quality of life for patients," said Western President Alan Shepard. "We are grateful for the Oberkotter Foundation's significant investment, which will help us maximize this new technology and accelerate the process of bringing this creative solution into standard practice."
The AI engine for pediatric earmold creation
For Emily's family, the ongoing cycle of audiology appointments for new earmolds has been a constant part of her son's childhood.
"He wears his earmolds every single day from the time he wakes up to the time he goes to bed," said Emily. "They go through a lot. On occasion, we've needed to replace an earmold because of wear and tear, and it can take 14 to 21 days to get earmolds back after an ear impression. Two weeks is a long time for him to have to wait to get his hearing back to where it needs to be."
Emily's son was part of the ALLEars pilot study, contributing his former earmolds to help researchers map how ears grow over time. Going forward, ALLEars researchers will gather thousands of impressions from other children, and these data will form the training set for the AI model.
Soodeh Nikan
"AI is able to learn features of the ear by examining a large ear impression dataset and translate this to predict the future shape of the ear," explained Soodeh Nikan, professor in the Faculty of Engineering and AI lead for the ALLEars project. "This is a first project of its kind to use AI technology for predictive earmold modeling."
The team is also developing a technique known as mirroring, where AI uses the shape of one ear to predict the shape of the other, an approach that could reduce the number of impressions young children must undergo.
"Repeating the ear impression process for both ears can be stressful on a child," said Nikan. "AI helps reduce the repetition of earmold impressions, so if a child receives an impression on the left ear, they don't need to repeat it for the right ear."
In addition to this work, researchers at Boys Town National Research Hospital are contributing their expertise in acoustic prediction to the project. Led by vice president of research Ryan McCreery, the team is using machine learning to determine how sound changes within the ear canal as children grow. This work will be added to the ALLEars project to ensure children receive the correct level of sound from their hearing aids.
Printing the future: open‑source manufacturing
Once the AI generates a predicted earmold, the file is sent to the researchers in Joshua Pearce's lab in the Faculty of Engineering at Western.
Joshua Pearce
There, postdoctoral research associate Alessia Romani is working on preparing the digital model for 3D printing. Translating a child's earmold from a digital file into a physical object requires suitable materials and advanced 3D‑printing strategies to ensure accuracy, comfort and reproducibility. The researchers aim to map out methods for producing earmolds at a much faster rate, with the potential for more accessible and low-cost production.
"The earmolds we're producing are extremely small, so we're trying to develop new methods - in software, firmware and hardware - to manufacture extremely small, but also resilient earmolds so that they can be used by children," said Pearce, a professor in the Faculty of Engineering and Ivey Business School.
The team is designing the workflow to develop AI-informed software, which will be openly shared with the hearing healthcare community worldwide. The goal for Pearce and the team is to enable as many people as possible to adopt the technology, especially in low‑ and middle‑income countries where access to earmold manufacturers is limited or nonexistent.
A global impact, starting in London
It's this commitment to making a difference for children in London, Ont. and around the world that motivates Emily. While her son's ears are no longer growing as rapidly as they were when he was a toddler, Emily sees the value of volunteering for the ALLEars project to support families at the beginning of their hearing‑aid journeys.
"The challenges with hearing loss aren't about the diagnosis; it's the barriers that get in the way. If the ALLEars project reduces those barriers - minimizing wait times and making it easier to get earmolds - it's going to impact families."
For Scollie, the potential is enormous.
"If we can reduce appointments, expand global access to earmold manufacturing and solve a daily clinical challenge for audiologists, it will be game‑changing. This project is a once‑in‑a‑lifetime opportunity."
